Search

Your search keyword '"Chen, Fuxing"' showing total 180 results
Start Over Author "Chen, Fuxing" Search Limiters Peer Reviewed
180 results on '"Chen, Fuxing"'

1. Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input Representation

Author

Finamore, Alessandro, Wang, Chao, Krolikowski, Jonatan, Navarro, Jose M., Chen, Fuxing, and Rossi, Dario

Subjects
Computer Science - Machine Learning, Computer Science - Networking and Internet Architecture
Abstract

Over the last years we witnessed a renewed interest toward Traffic Classification (TC) captivated by the rise of Deep Learning (DL). Yet, the vast majority of TC literature lacks code artifacts, performance assessments across datasets and reference comparisons against Machine Learning (ML) methods. Among those works, a recent study from IMC22 [16] is worth of attention since it adopts recent DL methodologies (namely, few-shot learning, self-supervision via contrastive learning and data augmentation) appealing for networking as they enable to learn from a few samples and transfer across datasets. The main result of [16] on the UCDAVIS19, ISCX-VPN and ISCX-Tor datasets is that, with such DL methodologies, 100 input samples are enough to achieve very high accuracy using an input representation called "flowpic" (i.e., a per-flow 2d histograms of the packets size evolution over time). In this paper (i) we reproduce [16] on the same datasets and (ii) we replicate its most salient aspect (the importance of data augmentation) on three additional public datasets (MIRAGE19, MIRAGE22 and UTMOBILENET21). While we confirm most of the original results, we also found a 20% accuracy drop on some of the investigated scenarios due to a data shift in the original dataset that we uncovered. Additionally, our study validates that the data augmentation strategies studied in [16] perform well on other datasets too. In the spirit of reproducibility and replicability we make all artifacts (code and data) available to the research community at https://tcbenchstack.github.io/tcbench/, Comment: to appear at ACM Internet Traffic Measurement (IMC) 2023, replication track

Published
2023
Full Text
View/download PDF

2. Cross-network transferable neural models for WLAN interference estimation

Author

Fernandes, Danilo Marinho, Krolikowski, Jonatan, Houidi, Zied Ben, Chen, Fuxing, and Rossi, Dario

Subjects
Computer Science - Networking and Internet Architecture, Computer Science - Artificial Intelligence
Abstract

Airtime interference is a key performance indicator for WLANs, measuring, for a given time period, the percentage of time during which a node is forced to wait for other transmissions before to transmitting or receiving. Being able to accurately estimate interference resulting from a given state change (e.g., channel, bandwidth, power) would allow a better control of WLAN resources, assessing the impact of a given configuration before actually implementing it. In this paper, we adopt a principled approach to interference estimation in WLANs. We first use real data to characterize the factors that impact it, and derive a set of relevant synthetic workloads for a controlled comparison of various deep learning architectures in terms of accuracy, generalization and robustness to outlier data. We find, unsurprisingly, that Graph Convolutional Networks (GCNs) yield the best performance overall, leveraging the graph structure inherent to campus WLANs. We notice that, unlike e.g. LSTMs, they struggle to learn the behavior of specific nodes, unless given the node indexes in addition. We finally verify GCN model generalization capabilities, by applying trained models on operational deployments unseen at training time.

Published
2022
Full Text
View/download PDF

3. A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification

Author

Fauvel, Kevin, Chen, Fuxing, and Rossi, Dario

Subjects
Computer Science - Machine Learning
Abstract

Traffic classification, i.e. the identification of the type of applications flowing in a network, is a strategic task for numerous activities (e.g., intrusion detection, routing). This task faces some critical challenges that current deep learning approaches do not address. The design of current approaches do not take into consideration the fact that networking hardware (e.g., routers) often runs with limited computational resources. Further, they do not meet the need for faithful explainability highlighted by regulatory bodies. Finally, these traffic classifiers are evaluated on small datasets which fail to reflect the diversity of applications in real-world settings. Therefore, this paper introduces a new Lightweight, Efficient and eXplainable-by-design convolutional neural network (LEXNet) for Internet traffic classification, which relies on a new residual block (for lightweight and efficiency purposes) and prototype layer (for explainability). Based on a commercial-grade dataset, our evaluation shows that LEXNet succeeds to maintain the same accuracy as the best performing state-of-the-art neural network, while providing the additional features previously mentioned. Moreover, we illustrate the explainability feature of our approach, which stems from the communication of detected application prototypes to the end-user, and we highlight the faithfulness of LEXNet explanations through a comparison with post hoc methods., Comment: Accepted for publication in the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Long Beach, USA, 2023

Published
2022

19. Finite element modeling of spherical indentation behavior of 3D mesh fabric at the yarn level.

Author

Zheng, Fei, Chen, Fuxing, and Liu, Yanping

Subjects
FINITE element method, YARN, NANOMECHANICS, TEXTILES
Abstract

This paper reports an experimental and numerical study on the spherical indentation behavior of three-dimensional (3D) warp-knitted mesh fabrics. A full-size finite element (FE) model of a typical 3D mesh fabric is established at the yarn level based on the realistic monofilament architecture from micro-computed tomography (μCT) scanning and verified with experiments. The structural change of the fabric in the spherical indentation process is quantitatively analyzed in terms of fabric global deformation, local deformation, mesh deformation, and spacer monofilament deformation from the FE simulation. The numerical results show that the fabric shrinks walewise and expands coursewise from the spherical indentation of the continuous intermeshed monofilament architecture, showing counterintuitive partial auxeticity. The coursewise symmetry and walewise asymmetry of the 3D mesh fabric produce relatively symmetrical coursewise deformation and asymmetrical walewise deformation under spherical indentation. The symmetrical coursewise deformation includes even widening, good fitting of the indenter, and almost identical mesh sizes in the coursewise direction. Walewise asymmetry leads to uneven shortening, inferior fitting of the indenter, and considerably varied mesh sizes in the walewise direction. Spacer monofilaments in different positions relative to the spherical indenter have different deformations. The closer to the indenter, the greater bending and twisting of the spacer monofilament. The spacer monofilament knitted earlier of the tested fabric has smaller deformation than that knitted later due to the walewise asymmetry. The coursewise symmetry and walewise asymmetry of the inhomogeneous 3D mesh fabric structure result in a highly nonlinear spherical indentation behavior. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

23. Semi-Centralized Name Routing Mechanism for Reconfigurable Network

Author

Chen, Fuxing, Liu, Weiyang, Li, Hui, Zhu, Zhipu, Akan, Ozgur, Series editor, Bellavista, Paolo, Series editor, Cao, Jiannong, Series editor, Coulson, Geoff, Series editor, Dressler, Falko, Series editor, Ferrari, Domenico, Series editor, Gerla, Mario, Series editor, Kobayashi, Hisashi, Series editor, Palazzo, Sergio, Series editor, Sahni, Sartaj, Series editor, Shen, Xuemin (Sherman), Series editor, Stan, Mircea, Series editor, Jia, Xiaohua, Series editor, Zomaya, Albert, Series editor, Leung, Victor C.M., editor, Chen, Min, editor, Wan, Jiafu, editor, and Zhang, Yin, editor

Published
2014
Full Text
View/download PDF

24. Optimization-Based Atomic Capability Routing Model for Flexible Architecture of Reconfigurable Infrastructure

Author

Liu, Weiyang, Li, Hui, Chen, Fuxing, Pan, Kai, Akan, Ozgur, Series editor, Bellavista, Paolo, Series editor, Cao, Jiannong, Series editor, Coulson, Geoff, Series editor, Dressler, Falko, Series editor, Ferrari, Domenico, Series editor, Gerla, Mario, Series editor, Kobayashi, Hisashi, Series editor, Palazzo, Sergio, Series editor, Sahni, Sartaj, Series editor, Shen, Xuemin (Sherman), Series editor, Stan, Mircea, Series editor, Jia, Xiaohua, Series editor, Zomaya, Albert, Series editor, Leung, Victor C.M., editor, Chen, Min, editor, Wan, Jiafu, editor, and Zhang, Yin, editor

Published
2014
Full Text
View/download PDF

25. Prologue: Unified Polymorphic Routing Towards Flexible Architecture of Reconfigurable Infrastructure

Author

Pan, Kai, Li, Hui, Liu, Weiyang, Zhu, Zhipu, Chen, Fuxing, Zhu, Bing, Akan, Ozgur, Series editor, Bellavista, Paolo, Series editor, Cao, Jiannong, Series editor, Coulson, Geoff, Series editor, Dressler, Falko, Series editor, Ferrari, Domenico, Series editor, Gerla, Mario, Series editor, Kobayashi, Hisashi, Series editor, Palazzo, Sergio, Series editor, Sahni, Sartaj, Series editor, Shen, Xuemin (Sherman), Series editor, Stan, Mircea, Series editor, Jia, Xiaohua, Series editor, Zomaya, Albert, Series editor, Leung, Victor C.M., editor, Chen, Min, editor, Wan, Jiafu, editor, and Zhang, Yin, editor

Published
2014
Full Text
View/download PDF

34. An experimental study on the vibration behavior and the physical properties of weft-knitted spacer fabrics manufactured using flat knitting technology.

Author

Chen, Fuxing, Wang, Ji, Gao, Shouwu, Ning, Xin, Yan, Pengxiang, and Tian, Mingwei

Subjects
SURGICAL gloves, TEXTILE technology, THREE-dimensional textiles, URETHANE foam, SPONGE (Material), FREQUENCIES of oscillating systems, KNITTING, VIBRATION isolation
Abstract

Weft-knitted spacer fabrics, a kind of three-dimensional fabric structure, are potential substitutes for typical rubber sponges and polyurethane foams for the protection of human body from exposure to vibrations. To explore the capability and the designability of weft-knitted spacer fabrics as the functional material of personal protective equipment against vibration, such as anti-vibration gloves and car cushions, the vibration behavior and physical properties of weft-knitted spacer fabrics manufactured using flat knitting technology were studied. In the first part of the article, the vibration behavior of top-loaded weft-knitted spacer fabric under harmonic base excitation was analyzed. The effects of monofilament diameter, linking distance and excitation acceleration level on the transmissibility curve of the mass-spacer fabric were evaluated. It was shown that to broaden the frequency range for vibration isolation, spacer fabrics with smaller monofilament diameter and longer linking distance were preferred. In the second part of the article, the effects of monofilament type, monofilament diameter, and spacer structure on the physical properties of spacer fabric including fabric shrinkage coefficient, fabric thickness, fabric stitch densities, and fabric areal mass were analyzed. It was found that fabric thickness was increased by employing spacer structures with longer linking distance and lower filling density of spacer monofilament. In addition, in order to obtain an optimized high fabric thickness, nylon monofilament was preferred to polyester monofilament. On the other hand, monofilament diameter has a significant influence on stitch densities and fabric areal mass. Larger monofilament diameter resulted in lower stitch densities and heavier areal mass for spacer fabric. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

38. Phillygenin, a MELK Inhibitor, Inhibits Cell Survival and Epithelial–Mesenchymal Transition in Pancreatic Cancer Cells

Author

Li, Hongchun, Chen, Miao, Yang, Zhuying, Wang, Qinxian, Wang, Jiesheng, Jin, Dong, Yang, Xiuyun, Chen, Fuxing, Zhou, Xiumin, and Luo, Kexue

Subjects
phillygenin, proliferation, pancreatic cancer, MELK, EMT, apoptosis, Original Research
Abstract

Introduction Pancreatic cancer (PC) is one of the leading causes of cancer, with the lowest 5-year survival rate of all cancer types. Given the fast metastasis of PC and its resistance to surgery, radiotherapy, chemotherapy, and combinations thereof, it is imperative to develop more effective anti-PC drugs. Phillygenin (PHI) has been reported to exert anti-cancer, anti-bacterial, and anti‐inflammatory properties. However, the mechanism of PHI in the development of PC is still unclear. Methods The cytotoxicity of PHI in pancreatic cancer cells was evaluated by MTT assay, and clonogenic assay was used to test the anti-proliferation of PHI. The pro-apoptotic effect of PHI was detected by flow cytometry analysis. The changes of epithelial–mesenchymal transition (EMT) in pancreatic cancer cells treated with PHI were determined by Western blot. Transwell assay was used to test the migration and invasion of PC cells after treatment with PHI. Molecular docking was used to predict the potential binding site of candidate target with PHI. Results PHI could inhibit the proliferation, migration, and EMT of PC cells (PANC-1 and SW1990) and induce its apoptosis. Analysis of the Cancer Genome Atlas database indicated that elevated MELK levels correlated with poor overall survival (OS) and disease-free survival (DFS) of PC patients. In addition, molecular modeling showed that PHI may potentially target the catalytic domain of maternal embryonic leucine zipper kinase (MELK). Overexpression of MELK muted the anti-PC effects of PHI. Conclusion PHI holds promise as a potent candidate drug for the treatment of PC via targeted MELK.

Published
2020

41. Pollution and carbon reduction effects of the carbon emissions trading mechanism in the context of the 'dual carbon' goals.

Author

LU Min, XU Hao, and CHEN Fuxing

Subjects
CARBON offsetting, CARBON emissions, EMISSIONS trading, EMISSIONS (Air pollution), POLLUTANTS, ENVIRONMENTAL quality
Abstract

As a key policy tool for China' s achievement of the goals of reaching peak carbon emissions and carbon neutrality, the carbon emissions trading mechanism has attracted widespread attention for its effect on reducing pollution and carbon emissions. This study incorporated carbon dioxide reduction and environmental pollution control into the same research framework. Based on the panel data of 30 provinces in China from 2010 to 2019, it took the carbon emissions trading mechanism as the policy background and used the improved entropy weight TOPSIS model to calculate the environmental pollution index to measure the local environmental quality and environmental pollution degree. The intersection term of carbon emissions and environmental pollution index was used to characterize the level of pollution reduction and carbon reduction. The difference-in-differences model and the synthetic control method were used to empirically test the pollution and carbon emission reduction effects of the carbon emissions trading mechanism. The results showed that: (1) From the perspective of the average treatment effect of the policy, the carbon emissions trading mechanism reduced the emissions of carbon dioxide and environmental pollutants in the pilot provinces compared with non-pilot provinces. After adding relevant control variables, the level of pollution and carbon reduction in the pilot provinces increased by 16%. From the perspective of the policy effects of pilot individuals, Beijing, Shanghai, Tianjin, and Chongqing performed better; that is, their carbon emissions showed a significant downward trend, followed by Guangdong, while Hubei performed worse. (2) The influential mechanisms and heterogeneity test revealed that the carbon emissions trading system achieved an increase in the synergistic governance level of pollution and carbon reduction through energy consumption restructuring and technological innovation. (3) Meanwhile, the pollution and carbon reduction levels showed regional heterogeneity, with the eastern and western regions performing best and the central region performing poorly. Furthermore, a grey correlation model was used to investigate the relationship between the pollution and carbon reduction levels and the potential for synergistic emission reduction in each province. The results found that the average correlation degree of Shanghai, Guangdong, Guangxi, Guizhou, and Xinjiang was greater than other provinces, showing a higher level and potential. Therefore, it is necessary to accelerate and improve the construction of the national carbon emissions trading market; give full play to the synergistic emissions reduction effects of market-based carbon emissions trading policies on carbon dioxide emissions and environmental pollutants; and accelerate the synergy of carbon emissions trading policies by increasing investment in technological innovation and the transformation and upgrading of energy consumption structures and formulating regionally differentiated carbon emission reduction policies. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results